© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46061
    Prev
    Next
    INDEX
    Explanations

    ways, ru, content, listening, maximum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĻħ
    -0.07
     round
    -0.07
    .batch
    -0.07
     Bias
    -0.07
     magn
    -0.07
     Sherman
    -0.06
    .ba
    -0.06
    èĬ¹
    -0.06
    åĽĬ
    -0.06
     concentrated
    -0.06
    POSITIVE LOGITS
    rosso
    0.10
    éģĵéķ¿
    0.09
    abit
    0.08
    Categ
    0.08
    èĢ¦
    0.08
    åģ¶
    0.08
    -config
    0.08
    kek
    0.08
    ucht
    0.08
    ç»Ī审
    0.08
    Activations Density 0.005%

    No Known Activations